返回
Image change detection from difference image through deterministic simulated annealing
DOI:10.1007/s10044-008-0110-5.png)
摘要
En 中文
This paper proposes an automatic method based on the deterministic simulated annealing (DSA) approach for solving the image change detection problem between two images where one of them is the reference image. Each pixel in the reference image is considered as a node with a state value in a network of nodes. This state determines the magnitude of the change. The DSA optimization approach tries to achieve the most network stable configuration based on the minimization of an energy function. The DSA scheme allows the mapping of interpixel contextual dependencies which has been used favorably in some existing image change detection strategies. The main contribution of the DSA is exactly its ability for avoiding local minima during the optimization process thanks to the annealing scheme. Local minima have been detected when using some optimization strategies, such as Hopfield neural networks, in images with large amount of changes, greater than the 20%. The DSA performs better than other optimization strategies for images with a large amount of changes and obtain similar results for images where the changes are small. Hence, the DSA approach appears to be a general method for image change detection independently of the amount of changes. Its performance is compared against some recent image change detection methods.
Keyword:
Image change detection
Difference images
Simulated annealing
Markov random fields
期刊
IF:
2
论文数:
1.9K
被引数:
1.9K
机构
引用论文
Genetic variation in vulnerability to the behavioral effects of neonatal hippocampal damage in rats.
Motion detection via change-point detection for cumulative histograms of ratio images通过变化点检测对比率图像的累积直方图进行运动检测
Crystal chemistry and metal-hydrogen bonding in anisotropic and interstitial hydrides of intermetallics of rare earth (R) and transition metals (T), RT3 and R2T7稀土 (R) 和过渡金属 (T) 的金属间化合物的各向异性和间隙氢化物中的晶体化学和金属氢键,RT3 和R2T7

